Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0375. Min Range: -7.0375
Max Act: 7.0375. Min Act: -0.1700
Data Index: 2866489 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.9750. Min Act: -0.1700
Data Index: 668820 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.9437. Min Act: -0.1700
Data Index: 4414534 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.9125. Min Act: -0.1700
Data Index: 8809665 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.8812. Min Act: -0.1700
Data Index: 1933404 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.9125. Min Act: -0.1700
Data Index: 6052998 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.8500. Min Act: -0.1700
Data Index: 6149778 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.7875. Min Act: -0.1700
Data Index: 2730954 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.7562. Min Act: -0.1700
Data Index: 4270196 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.7562. Min Act: -0.1700
Data Index: 2379198 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.7562. Min Act: -0.1700
Data Index: 8236483 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6937. Min Act: -0.1700
Data Index: 647579 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.7250. Min Act: -0.1700
Data Index: 1008889 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6937. Min Act: -0.1700
Data Index: 259241 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6937. Min Act: -0.1700
Data Index: 2706003 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6625. Min Act: -0.1700
Data Index: 2243259 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6625. Min Act: -0.1700
Data Index: 3705598 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6000. Min Act: -0.1700
Data Index: 2466074 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6312. Min Act: -0.1700
Data Index: 1303241 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0375. Min Range: -7.0375
Max Act: 6.6312. Min Act: -0.1700
Data Index: 8109562 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19